15 October 2012 Rotation invariant fast features for large-scale recognition
Author Affiliations +
Abstract
We present an end-to-end feature description pipeline which uses a novel interest point detector and Rotation- Invariant Fast Feature (RIFF) descriptors. The proposed RIFF algorithm is 15× faster than SURF1 while producing large-scale retrieval results that are comparable to SIFT.2 Such high-speed features benefit a range of applications from Mobile Augmented Reality (MAR) to web-scale image retrieval and analysis.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gabriel Takacs, Gabriel Takacs, Vijay Chandrasekhar, Vijay Chandrasekhar, Sam Tsai, Sam Tsai, David Chen, David Chen, Radek Grzeszczuk, Radek Grzeszczuk, Bernd Girod, Bernd Girod, "Rotation invariant fast features for large-scale recognition", Proc. SPIE 8499, Applications of Digital Image Processing XXXV, 84991D (15 October 2012); doi: 10.1117/12.945968; https://doi.org/10.1117/12.945968
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

CBIR: from low-level features to high-level semantics
Proceedings of SPIE (April 18 2000)
Real-time traffic sign detection and recognition
Proceedings of SPIE (January 18 2009)
Video and image retrieval beyond the cognitive level the...
Proceedings of SPIE (December 31 2000)
Optimized filterbank fingerprint recognition
Proceedings of SPIE (May 27 2003)

Back to Top